Speed Enhancement of Free-form Curve Matching with Parallel Fortran 2008

被引：0
作者：
Stamos, A. A. [1 ]
Vassilaki, D. I. [2 ]
Ioannidis, Ch. C. [2 ]
机构：
[1] Natl Tech Univ Athens, Sch Civil Engn, GR-10682 Athens, Greece
[2] Natl Tech Univ Athens, Sch Rural & Surveying Engn, GR-10682 Athens, Greece
来源：
PROCEEDINGS OF THE FIRST INTERNATIONAL CONFERENCE ON PARALLEL, DISTRIBUTED AND GRID COMPUTING FOR ENGINEERING | 2009年 / 90期
关键词：
parallelization; multiprocessing; cluster; image registration; matching; REGISTRATION;
D O I：
暂无
中图分类号：
TP39 [计算机的应用];
学科分类号：
081203 ; 0835 ;
摘要：
Free-form curves matching, which has countless applications, is done by an in-house developed algorithm based on the Iterative Closest Point (ICP) algorithm. The algorithm splits the curves to a large number of consecutive interpolated points and seeks closest points pairs between them. It is shown that the, processor intensive, matching algorithm benefits from parallelization, splitting each ICP iteration to potentially hundreds of almost independent groups. The algorithm is implemented using coarrays of the upcoming Fortran 2008 standard, and runs in standard hardware. An example of complex curves matching, run in a small computer cluster, shows promising results
引用
收藏
页码：193 / +
页数：3
相关论文
共 13 条
[1]   A METHOD FOR REGISTRATION OF 3-D SHAPES [J].
BESL, PJ ;
MCKAY, ND .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1992, 14 (02) :239-256
[2]  
CHIVERS I, 2000, FORTRAN 95
[3]  
REID J, 2008, JTCLSC22WG5 UK ISOIE
[4]  
Stamos A. A., 2007, P EUROPYTHON2007 C V
[5]  
Tanenbaum S., 1992, MODERN OPERATING SYS
[6]  
*US FORTR COMM, 2007, J307007R3 US FORTR C
[7]  
VASSILAKI D, 2008, 3 INT C SCI COMP COM
[8]  
VASSILAKI D, 2008, DIGITAL EARTH SUMMIT, P141
[9]  
VASSILAKI D, 2009, REGISTRATION HETEROG
[10]  
VASSILAKI D.I, 2008, EARSELS WORKSH REM S, P141
12